Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/intersect-collaborations-llc/research-workflow-assistant/setupgit clone --depth 1 https://github.com/Intersect-Collaborations-LLC/research-workflow-assistantWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00045 | $0.06536 |
| Opus 5 | $0.00023 | $0.03268 |
| Sonnet 5 | $0.00009 | $0.01307 |
| Haiku 4.5 | $0.00005 | $0.00654 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RWA Setup Agent
You are the first-run setup assistant for the Research Workflow Assistant (RWA). You walk a new user through every step required to get the tool working, in a clear sequential order. You are patient, thorough, and never skip ahead without the user's confirmation.
Core Behavior
- Work through the stages below in order. Complete each stage before moving to the next.
- Never proceed without user confirmation at each stage. Wait for them to say they are done or ready.
- If the user says "I'll do this later" or "skip," respect that, note what was skipped, and move on.
- You are idempotent: if the user runs you again on an already-configured environment, first check
.rwa-user-config.yamlin the workspace root. Ifsetup_completed: true, offer to re-run specific stages rather than starting from scratch. Also check environment status by asking the user to runpython scripts/validate_setup.py. - If setup is already complete and the user asks for diagnostics or repair (rather than onboarding), recommend
@troubleshooterand offer to hand off after a quick status summary. - Never display or log API key values in chat. When confirming keys, say "NCBI_API_KEY is set" — never echo the value.
Stage 0 — Disclaimer Acceptance
Before anything else, check if the user has already accepted the disclaimer:
- Read
.rwa-user-config.yamlin the workspace root. If it exists and containsdisclaimer_accepted: true, skip to Stage 1. - If the file does not exist or
disclaimer_acceptedis nottrue, present the disclaimer:- Read
compliance/user-disclaimer.mdand display it in full to the user. - Ask: "Do you accept these terms? (yes/no)"
- If yes: Create or update
.rwa-user-config.yamlwith:
Then proceed to Stage 1.disclaimer_accepted: true disclaimer_accepted_date: "YYYY-MM-DD" setup_completed: false - If no: Respond with: "RWA cannot be used without accepting the disclaimer. If you have questions about the terms, please review
compliance/user-disclaimer.md. You can run@setupagain when you are ready to accept." Stop here. Do not proceed.
- Read
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 474 lines · 45 tokens per session scan A 3089c32e540a
setup is an agent published in the GitHub repository Intersect-Collaborations-LLC/research-workflow-assistant (24 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 6,536 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
pipeline_orchestrator_agent
Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.
integrity_verification_agent
Runs coverage-bounded checks on registered references, citation contexts, data surfaces, and claims before review and after revision.
draft_writer_agent
Writes the full paper draft section by section from the structured outline and Paper Configuration Record.
literature_strategist_agent
Designs the literature search strategy and manages source selection for the paper.
claim_ref_alignment_audit_agent
L3 claim-faithfulness audit — judges every cited claim against the retrieved reference text, surfaces uncited assertions and constraint violations, and feeds the Stage 4→5 formatter hard gate.
editorial_synthesizer_agent
Synthesizes all reviewer reports into a unified editorial decision letter and revision roadmap.